Tesslate/WEBGEN-4B-Preview
Full fine-tune vs Qwen/Qwen3-4B-Instruct-2507. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 94/145, MLP 108/108, Attention 144/144
5 derivatives checked
- gabriellarson/WEBGEN-4B-Preview-GGUF: Same weights, converted
- mradermacher/WEBGEN-4B-Preview-i1-GGUF: Quantization
- prithivMLmods/WEBGEN-4B-Preview-f32-GGUF: Same weights, converted
- mradermacher/WEBGEN-4B-Preview-GGUF: Same weights, converted
- DevQuasar/Tesslate.WEBGEN-4B-Preview-GGUF: Same weights, converted